3D object detection in point clouds using only 2D image labels for training with RCV
Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations
arXiv paper abstract https://arxiv.org/abs/2211.07108
arXiv PDF paper https://arxiv.org/ftp/arxiv/papers/2211/2211.07108.pdf
Heavily relying on 3D annotations limits the real-world application of 3D object detection.
... propose a method that does not demand any 3D annotation, while being able to predict full-oriented 3D bounding boxes.
... method, called Recursive Cross-View (RCV), transforms 3D detection into several 2D detection tasks, which only consume some 2D labels, based on the three-view principle.
... a frustum is proposed via a 2D detector, followed by the recursive paradigm that finally outputs a full-oriented 3D box, class, and score.
... method achieves comparable performance with some full 3D supervised learning methods.
RCV is the first 3D detection method that does not consume 3D labels and yields full-oriented 3D boxes on point clouds.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments